Block a user
Spike: prove a license-safe, performance-parity Mojo-Metal integration
based on this findings - especially the license topics - all work on MOJO is cancelled.
Spike: prove a license-safe, performance-parity Mojo-Metal integration
Spike: prove a license-safe, performance-parity Mojo-Metal integration
Implemented and pushed in 0dcf181.
Decision: STOP at the mandatory license/runtime gate. Mojo is pinned to 1.0.0 (Mojo 1.0.0 (ed45d567)) through uv.lock, with a one-command proof at…
Spike: prove a license-safe, performance-parity Mojo-Metal integration
Optional follow-up: add CUDA to the completed Mojo backend
Complete the Mojo release matrix, packaging, cutover, and native-backend retirement
Add Qwen3.8 MTP and multimodal inference without regressing the text path
Implement the GLM 5.2 Mojo backend with isolated sparse-path parity gates
Add a performance-parity Qwen3.8-27B Q4 and Q8 text backend in Mojo
Implement the shared Mojo foundation and a quantized routed-MoE vertical slice
Implement the complete DeepSeek Mojo backend with native performance parity
Build the native-versus-Mojo parity harness and operation coverage inventory
Spike: prove a portable Mojo GPU integration without losing native performance
Add a native glob tool for agent file discovery
Add a native glob tool for agent file discovery
Implemented and pushed as 5c74739.
- Added the native, read-only glob(pattern, path, max_results) tool through the existing generated schema, validation, and execution path. Basename and…